📚 publications

2020

1. 

   A framework for quantifying and characterising road accident risk: A data mining approach

   S.A. Heerden

   Stellenbosch University, Mar 2020

   Promotor: Prof J.H. van Vuuren, Co-promotor: Prof S.S. Grobbelaar

   Abs Bib HTML PDF

   According to the World Health Organisation, road accidents account for approximately 1.25 million deaths annually — the eighth leading cause of death worldwide. With the enormous losses to society resulting from road accidents, the prevention and severity reduction of road accidents has been an active area of research focus for many decades. Researchers frequently employ a variety of statistical learning techniques in an attempt to understand the factors contributing to higher levels of road accident risk. Such insights provide vital direction for governments with respect to safer road designs and the establishment of countermeasures aimed at reducing the number of road accidents. Furthermore, recent advances in machine learning have presented exciting new machine learning possibilities that were deemed far out of reach just over a decade ago. The tasks associated with data pre-processing in this context are, however, often daunting and immensely time-consuming. Moreover, the adoption of machine learning models in the road accident analysis literature has been relatively limited due to the uninterpretable nature of the majority of these models.
   
   A generic modular data mining framework is, therefore, proposed in this dissertation, aimed specifically at formalising and facilitating the tasks associated with road accident data preparation, and facilitating the interpretation of machine learning model output. This framework is designed to facilitate the configuration, enhancement and transformation of raw accident, vehicle, road and victim data into useful information which appropriately quantifies and characterises road accident risk. More specifically, this framework facilitates evaluation of road accident risk in terms of the rate and severity of being involved in a road accident along road segments and at road junctions based on historically recorded RAs. The configuration procedure in the proposed framework allows a user to format data attributes appropriately, as well as correct any missing or erroneous values that may exist in data sets. The enhancement procedure allows a user to merge vehicle and road records to a corresponding accident record for the purpose of creating an all-encompassing data set. It is also possible to construct new attributes based on current attribute values residing in the aforementioned data sets. After each of the individual data sets has been prepared appropriately and the data are deemed of a sufficiently high quality, they may be stored in a database. Finally, the transformation procedure exploits these high-quality data to quantify the rate and severity of road accidents along road segments or at road junctions. These results serve as input to a standard supervised learning procedure in which road characteristics are used to predict these rate and severity measurements.
   
   In order to demonstrate the practical workability and usefulness of the proposed framework, a concept demonstrator of the framework is implemented in an existing data mining platform and applied to a real-world case study based on road accident data from Greater Manchester in the United Kingdom. Each of the individual data preparation components of the framework is tested in the context of this case study, while the effectiveness of the road accident risk evaluation approaches is demonstrated by means of multiple investigations.

   @phdthesis{vanheerden2020_1,
     title = {A framework for quantifying and characterising road accident risk: A data mining approach},
     author = {van Heerden, S.A.},
     school = {Stellenbosch University},
     year = {2020},
     month = mar,
     note = {Promotor: Prof J.H. van Vuuren, Co-promotor: Prof S.S. Grobbelaar},
   }

2. 

   Towards a descriptive model of road accident risk (preprint)

   Submitted to: Accident Analysis & Prevention, Mar 2020

   Abs Bib PDF

   With the enormous losses to society resulting from road accidents (RAs), their prevention and severity reduction has been an active area of research focus for many decades. Over the years, researchers have proposed a wide variety of principles and models related to road safety, many of which attempt to draw insights from historical RA and exposure data. In this paper, a novel descriptive model is proposed for quantifying the risk posed by various roadway characteristics along a road network which takes inspiration from the three dimensions of road safety and employs network Kernel Density Estimation (KDE). Risk, in this context, is modelled as both the rate and severity of being involved in an RA. The proposed methodology is applied to a real-world case study based on public accident and road data so as to demonstrate its intended functionality in the context of a realistic setting.

   @article{vanheerden2020_2,
     title = {Towards a descriptive model of road accident risk (preprint)},
     author = {},
     journal = {Submitted to: Accident Analysis & Prevention},
     year = {2020},
   }

2019

1. 

   The Western Cape Chapter

   S.A. Heerden

   Mar 2019

   Bib HTML PDF

   @inbook{kruger2019,
     booktitle = {Operations research in South Africa: The first 50 years},
     title = {The Western Cape Chapter},
     chapter = {5.3},
     pages = {151--156},
     author = {van Heerden, S.A.},
     editor = {Kruger, H.A. and van Vuuren, J.H.},
     publisher = {African SunMedia},
     address = {Stellenbosch},
     year = {2019},
     isbn = {9780620847216},
   }

2018

1. 

   Optimisation of stock keeping unit placement in a retail distribution centre

   S.A. Heerden, and J.H. Vuuren

   South African Journal of Industrial Engineering, Mar 2018

   Abs Bib HTML PDF

   The retail problem of slotting refers to the assignment of stock keeping units (SKUs) to the available storage locations in a distribution centre (DC). Generally, the expected total distance travelled by stock pickers during an order consolidation and the resulting level of congestion experienced within aisle racking are common considerations when making these assignments. These criteria give rise to a bi-objective optimisation model with the aim of identifying multiple stock setups that achieve acceptable tradeoffs between minimising the criteria on expectation. A mathematical framework is established in this paper, based on these two criteria, for evaluating the effectiveness of a given stock setup. In the framework, a stock picker’s movement between various storage locations is modelled as a Markov chain in order to quantify his or her expected travel distance, while a closed queuing network model is used to devise a suitable measure of congestion. This optimisation model framework forms the basis of a flexible decision support system (DSS) for the purpose of discovering high-quality stock assignment trade-off solutions for inventory managers. The DSS is applied to a special case study involving data from a real DC, and the desirability of the recommended stock configurations is compared with that currently implemented within the DC.

   @article{vanheerden2018,
     title = {Optimisation of stock keeping unit placement in a retail distribution centre},
     author = {van Heerden, S.A. and van Vuuren, J.H.},
     journal = {South African Journal of Industrial Engineering},
     volume = {29},
     number = {2},
     pages = {74--91},
     year = {2018},
     doi = {10.7166/29-2-1867},
   }